Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 4936 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 2.1319. Min Range: -2.1319

Max Act: 2.1319. Min Act: -0.0000

Data Index: 10725 (C4 (Web Text))

Max Activating Token Index: 734

Text #1

Max Range: 2.1319. Min Range: -2.1319

Max Act: 1.8595. Min Act: -0.0000

Data Index: 721513 (C4 (Web Text))

Max Activating Token Index: 487

Text #2

Max Range: 2.1319. Min Range: -2.1319

Max Act: 1.8478. Min Act: -0.0000

Data Index: 1117455 (C4 (Web Text))

Max Activating Token Index: 691

Text #3

Max Range: 2.1319. Min Range: -2.1319

Max Act: 1.5673. Min Act: -0.0000

Data Index: 1203744 (C4 (Web Text))

Max Activating Token Index: 682

Text #4

Max Range: 2.1319. Min Range: -2.1319

Max Act: 1.6274. Min Act: -0.0000

Data Index: 133482 (C4 (Web Text))

Max Activating Token Index: 940

Text #5

Max Range: 2.1319. Min Range: -2.1319

Max Act: 1.4648. Min Act: -0.0000

Data Index: 916365 (C4 (Web Text))

Max Activating Token Index: 945

Text #6

Max Range: 2.1319. Min Range: -2.1319

Max Act: 1.4535. Min Act: -0.0000

Data Index: 789755 (C4 (Web Text))

Max Activating Token Index: 894

Text #7

Max Range: 2.1319. Min Range: -2.1319

Max Act: 1.5840. Min Act: -0.0000

Data Index: 522003 (C4 (Web Text))

Max Activating Token Index: 1008

Text #8

Max Range: 2.1319. Min Range: -2.1319

Max Act: 1.4690. Min Act: -0.0000

Data Index: 286448 (C4 (Web Text))

Max Activating Token Index: 211

Text #9

Max Range: 2.1319. Min Range: -2.1319

Max Act: 1.2900. Min Act: -0.0000

Data Index: 175363 (C4 (Web Text))

Max Activating Token Index: 527

Text #10

Max Range: 2.1319. Min Range: -2.1319

Max Act: 1.1936. Min Act: -0.0000

Data Index: 1433953 (Python Code)

Max Activating Token Index: 249

Text #11

Max Range: 2.1319. Min Range: -2.1319

Max Act: 1.3553. Min Act: -0.0000

Data Index: 294454 (C4 (Web Text))

Max Activating Token Index: 125

Text #12

Max Range: 2.1319. Min Range: -2.1319

Max Act: 1.2490. Min Act: -0.0000

Data Index: 1076673 (C4 (Web Text))

Max Activating Token Index: 984

Text #13

Max Range: 2.1319. Min Range: -2.1319

Max Act: 1.2345. Min Act: -0.0000

Data Index: 1060393 (C4 (Web Text))

Max Activating Token Index: 202

Text #14

Max Range: 2.1319. Min Range: -2.1319

Max Act: 1.2034. Min Act: -0.0000

Data Index: 1650599 (Python Code)

Max Activating Token Index: 194

Text #15

Max Range: 2.1319. Min Range: -2.1319

Max Act: 1.1723. Min Act: -0.0000

Data Index: 1569313 (Python Code)

Max Activating Token Index: 958

Text #16

Max Range: 2.1319. Min Range: -2.1319

Max Act: 1.1952. Min Act: -0.0000

Data Index: 614144 (C4 (Web Text))

Max Activating Token Index: 727

Text #17

Max Range: 2.1319. Min Range: -2.1319

Max Act: 1.0514. Min Act: -0.0000

Data Index: 539167 (C4 (Web Text))

Max Activating Token Index: 212

Text #18

Max Range: 2.1319. Min Range: -2.1319

Max Act: 1.0985. Min Act: -0.0000

Data Index: 761368 (C4 (Web Text))

Max Activating Token Index: 310

Text #19

Max Range: 2.1319. Min Range: -2.1319

Max Act: 1.1036. Min Act: -0.0000

Data Index: 1462965 (Python Code)

Max Activating Token Index: 42